Use case · Free plugin
My agent ran the tests and the log filled the window. Now the model reads the failing tests.
The free context-mode plugin runs test, lint and build output in a sandbox on your machine. A short script picks the failing tests, the error lines and the counts. On a Vite run of 1,106 tests, 61.4 KB of output reached the model as 0.4 KB.
Full log: every test name, stack trace and timing line reaches the model.
Every later call sends it again.
Free plugin: a script reads the log in a sandbox on your machine.
Sent to the model
- The 25 failing tests, the first error of each and the file to open
Kept on your machine
- The full 61.4 KB log, searchable with ctx_search
The answer is a short list. The log is long.
A verbose run prints each test name, each stack trace and each timing line.
The failing tests, the first error of each and the file to open.
Text in the conversation goes back to the model on every later call of the session.
A script reads the log. The model reads the list.
- 01The output goes to the sandbox
Your agent calls
ctx_executewith the command, or the PostToolUse hook catches a large shell output. - 02A short script reads it
The agent writes the script. It prints the failing tests and their first error line.
- 03The model reads the print
The full output goes into a SQLite FTS5 index in
~/.context-mode. The agent finds a stack trace later withctx_search.
Five logs, measured. The model reads under 1 KB of each.
| Log | Full output | The model read | Time |
|---|---|---|---|
Test run, 1,106 tests, 25 failing (vitest run --reporter=verbose, vitejs/vite) | 61.4 KB | 0.4 KB | 60 ms |
Lint report as JSON (biome lint --reporter=json, packages/vite/src) | 281.8 KB | 0.6 KB | 65 ms |
Workspace install log (pnpm install --frozen-lockfile, vitejs/vite) | 14.6 KB | 0.2 KB | 59 ms |
Database server log (docker logs, mongo:8.0 --verbose) | 59.0 KB | 0.6 KB | 62 ms |
Infrastructure plan (terraform plan, 72 resources) | 33.3 KB | 0.2 KB | 62 ms |
Plugin benchmark of 2026-11-01 on an Apple M1 Pro, default settings, median of 5 runs. Raw data: the result tables. Rerun it with the steps on Benchmarks.
Give your agent one of these.
Run the full test suite. Give me each failing test, its first error line and the file to fix. Then fix them one at a time and run the suite again.
Run the linter on src. Group the findings by rule, show the count for each rule, and fix the rule with the most findings.
Run terraform plan and list each resource it will replace or destroy, with the reason the plan gives.
What this uses.
Open source. It runs in your agent, on your machine.
Where the command runs and what comes back.
How the agent finds a line in the full log later.
Read the failing tests. Keep the full log on your machine.
Each agent installs the free plugin with its own install command.